{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "start_time": "2023-05-04T09:29:48.650911Z",
     "end_time": "2023-05-04T09:29:49.231339Z"
    }
   },
   "outputs": [],
   "source": [
    "from IPython.core.interactiveshell import InteractiveShell  #执行该代码可以使得当前nb支持多输出\n",
    "InteractiveShell.ast_node_interactivity = \"all\" \n",
    "import numpy as np\n",
    "import pandas as pd  \n",
    "import re "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**作业1**\n",
    "\n",
    "利用pandas读入csv数据，求化合物的分子式和质量"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "start_time": "2023-05-04T09:31:30.790867Z",
     "end_time": "2023-05-04T09:31:34.398474Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The compand is composed of :  ['Calcium', 'Carbon', 'Oxygen']\n",
      "  symbol  num     name  atomicMass\n",
      "0     Ca    1  Calcium      40.078\n",
      "1      C    1   Carbon      12.011\n",
      "2      O    3   Oxygen      15.999\n",
      "The atomic mass of the compound is  100.0869\n"
     ]
    }
   ],
   "source": [
    "# 元素周期表文件，给出任意一个化学表达式，计算其分子元素和质量。输出结果（不得再用C-O2作为输入）：\n",
    "\n",
    "import csv\n",
    "def readTable(fileObj):\n",
    "    # 使用pandas reader读取文件对象\n",
    "    df = pd.read_csv(fileObj, index_col='symbol')\n",
    "    return df\n",
    "            \n",
    "def parserElement(elementStr, table):\n",
    "    # 用 split 方法分割'-'成为数组\n",
    "    elements = elementStr.split('-')\n",
    "    # 初始化函数作用域内变量\n",
    "    names = []\n",
    "    atomicMass_lst = []\n",
    "    symbols = []\n",
    "    numbers = []\n",
    "    mass = 0\n",
    "    # 遍历数组，找寻元素\n",
    "    for element in elements:\n",
    "        # 用正则表达式分离字母与数字 用join把列表连接\n",
    "        number = ''.join(re.findall(r'\\d+', element))\n",
    "        symbol = ''.join(re.findall(r'[^\\d]+', element))\n",
    "        symbols.append(symbol)\n",
    "        # 将元素名称加入数组\n",
    "        names.append(table.loc[symbol]['name'])\n",
    "        # 索引出质量\n",
    "        atomicMass = eval(re.sub(r'\\([^)]*\\)', '', table.loc[symbol]['atomicMass']))\n",
    "        atomicMass_lst.append(atomicMass)\n",
    "        # 判断数量是否为1\n",
    "        if number:\n",
    "            number = int(number)\n",
    "        else:\n",
    "            number = 1\n",
    "        numbers.append(number)\n",
    "        mass += atomicMass * number\n",
    "    # 新建表格\n",
    "    df = pd.DataFrame()\n",
    "    df['symbol'] = symbols\n",
    "    df['num'] = numbers\n",
    "    df['name'] = names\n",
    "    df['atomicMass'] = atomicMass_lst\n",
    "\n",
    "    print('The compand is composed of : ', names)\n",
    "    print(df)\n",
    "\n",
    "    print('The atomic mass of the compound is ', mass)\n",
    "\n",
    "fileHandle = open('periodic-table.csv','r')\n",
    "periodicTable = readTable(fileHandle)\n",
    "\n",
    "compountString  = input('Input a chemical compound, hyphenated,eg. C-O2:')\n",
    "parserElement(compountString, periodicTable)\n",
    "\n",
    "fileHandle.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "metadata": {
  "hide_input": false,
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}